發(fā)布時間：2018-11-05 11:46

【摘要】：近些年以來,中國、美國、印度等國家發(fā)生了多起大面積停電事故,造成了巨大的經(jīng)濟損失和社會影響�？稍偕茉�、電力負荷的進一步增長、電力系統(tǒng)中電力電子化的廣泛應用等增加了電網(wǎng)運行的不確定性和復雜性,電網(wǎng)安全穩(wěn)定運行面臨著嚴峻的挑戰(zhàn)。隨著人工智能、深度學習的興起,為研究人員從大數(shù)據(jù)、大樣本、概率學的角度分析電網(wǎng)信息物理系統(tǒng)的安全穩(wěn)定性,提供了堅實的理論基礎(chǔ)。本文采用深度卷積網(wǎng)絡(luò)(CNN)技術(shù),通過構(gòu)建可視化的全信息電網(wǎng)圖,將CNN方法引入到電力系統(tǒng)暫態(tài)安全穩(wěn)定性分析中。并在總結(jié)分析前人工作的基礎(chǔ)上,結(jié)合支路勢能的方法,解釋了系統(tǒng)暫態(tài)可視化過程中電網(wǎng)“撕裂”特征的機理,并提出快速判斷電力系統(tǒng)薄弱斷面以及暫態(tài)穩(wěn)定性快速判別的方法�；诳梢暬约袄碚摲治龅某晒�,構(gòu)建了深度卷積神經(jīng)網(wǎng)絡(luò)對系統(tǒng)暫態(tài)穩(wěn)定進行分析,實現(xiàn)電力系統(tǒng)暫態(tài)穩(wěn)定快速評估。本文主要包括以下內(nèi)容:(1)構(gòu)建了動態(tài)可視化的電網(wǎng)圖。建立了基于電壓復平面的電力系統(tǒng)映射平面,以IEEE 10機39節(jié)點為例,獲取其仿真數(shù)據(jù)以及已有拓撲連接關(guān)系,基于Echart實現(xiàn)該系統(tǒng)節(jié)點信息在電壓復平面上動態(tài)展示。(2)建立了基于電壓復平面動態(tài)信息的電力系統(tǒng)暫態(tài)穩(wěn)定分析模型。從薄弱斷面的角度,分析了電壓相量距離和振蕩中心落點支路的關(guān)系,給出快速識別薄弱斷面的方法。在此基礎(chǔ)上,進一步分析了薄弱斷面領(lǐng)先機群側(cè)母線的相軌跡特征,提出了基于薄弱斷面兩端母線相軌跡特征的暫態(tài)穩(wěn)定性判別方法。(3)開發(fā)了樣本批量制造程序,為深度學習提供足夠的樣本。借鑒深度學習方法在人工視覺領(lǐng)域處理數(shù)據(jù)的方法,以處理圖片像素矩陣的角度,將深度學習的方法應用于電力系統(tǒng)暫態(tài)穩(wěn)定性評估。通過實驗的方法,確定了合適的模型參數(shù),提出了多窗口滑動識別電力系統(tǒng)暫態(tài)穩(wěn)定性的方式,減少了模型的參數(shù)并提升了判斷準確率。
[Abstract]:In recent years, China, the United States, India and other countries have had a number of large-scale power outages, resulting in huge economic losses and social impact. With the further growth of renewable energy, power load and the wide application of electronization in power system, the uncertainty and complexity of power grid operation are increased, so the safe and stable operation of power network is facing severe challenges. With the rise of artificial intelligence and deep learning, it provides a solid theoretical basis for researchers to analyze the security and stability of power grid information physical systems from the perspective of big data, large samples and probabilities. In this paper, the deep convolution network (CNN) technique is used to construct a visual full information grid diagram, and the CNN method is introduced to the transient security stability analysis of power system. On the basis of summing up and analyzing the previous work, combined with the method of branch potential energy, the mechanism of power grid "tearing" in the process of system transient visualization is explained. A fast method for judging the weak section and transient stability of power system is proposed. Based on the results of visualization and theoretical analysis, a deep convolution neural network is constructed to analyze the transient stability of power system. The main contents of this paper are as follows: (1) A dynamic visual grid diagram is constructed. The power system mapping plane based on voltage complex plane is established. Taking 39 nodes of IEEE 10 machine as an example, the simulation data and the existing topology connection are obtained. The node information of the system is dynamically displayed on the voltage complex plane based on Echart. (2) the power system transient stability analysis model based on the voltage complex plane dynamic information is established. From the point of view of weak section, the relationship between the voltage phasor distance and the branch of the oscillation center drop point is analyzed, and the method to identify the weak section quickly is given. On this basis, the phase locus characteristics of the side bus of the weak section leading cluster are further analyzed, and a method of judging transient stability based on the phase trace characteristics of the weak section is proposed. (3) A batch manufacturing program is developed. Provide enough samples for deep learning. The depth learning method is applied to power system transient stability evaluation by using depth learning method for data processing in artificial vision field to deal with image pixel matrix. Through the experimental method, the suitable model parameters are determined, and a multi-window sliding identification method is proposed to identify the transient stability of power system, which reduces the parameters of the model and improves the accuracy of judgment.
【學位授予單位】：中國電力科學研究院
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TM712

【參考文獻】

相關(guān)期刊論文 前10條

1 馬世龍;烏尼日其其格;李小平;;大數(shù)據(jù)與深度學習綜述[J];智能系統(tǒng)學報;2016年06期

2 邵瑤;湯涌;易俊;王安斯;;土耳其“3·31”大停電事故分析及啟示[J];電力系統(tǒng)自動化;2016年23期

3 李柏青;劉道偉;秦曉輝;嚴劍峰;;信息驅(qū)動的大電網(wǎng)全景安全防御概念及理論框架[J];中國電機工程學報;2016年21期

4 鄭超;苗田;;交流薄弱斷面中關(guān)鍵支路動態(tài)識別及穩(wěn)定控制[J];中國電機工程學報;2015年21期

5 岑炳成;唐飛;廖清芬;晏陽;唐昱恒;董飛飛;李瑾瑜;;應用功角空間降維變換的相軌跡判別系統(tǒng)暫態(tài)穩(wěn)定性[J];中國電機工程學報;2015年11期

6 茍競;劉俊勇;Gareth Taylor;Christopher Saunders;劉友波;劉洋;;基于發(fā)電機對暫態(tài)勢能集的電力系統(tǒng)暫態(tài)穩(wěn)定快速評估[J];電網(wǎng)技術(shù);2015年02期

7 劉道偉;張東霞;孫華東;馬世英;李柏青;朱朝陽;易俊;鄭超;秦曉輝;許鵬飛;楊學濤;;時空大數(shù)據(jù)環(huán)境下的大電網(wǎng)穩(wěn)定態(tài)勢量化評估與自適應防控體系構(gòu)建[J];中國電機工程學報;2015年02期

8 王亞俊;王波;唐飛;陳得治;王靜;王乙斐;周雨田;;基于響應軌跡和核心向量機的電力系統(tǒng)在線暫態(tài)穩(wěn)定評估[J];中國電機工程學報;2014年19期

9 楊勝春;湯必強;姚建國;李峰;於益軍;馮樹海;;基于態(tài)勢感知的電網(wǎng)自動智能調(diào)度架構(gòu)及關(guān)鍵技術(shù)[J];電網(wǎng)技術(shù);2014年01期

10 顧卓遠;湯涌;孫華東;劉楠;秦曉輝;張妍;;一種基于轉(zhuǎn)速差 功角差變化趨勢的暫態(tài)功角穩(wěn)定辨識方法[J];中國電機工程學報;2013年31期

相關(guān)博士學位論文 前1條

1 葉圣永;基于機器學習的電力系統(tǒng)暫態(tài)穩(wěn)定評估研究[D];西南交通大學;2010年

相關(guān)碩士學位論文 前2條

1 黎萌;電力系統(tǒng)暫態(tài)穩(wěn)定時域仿真終止判據(jù)的研究[D];浙江大學;2015年

2 杜浩;基于網(wǎng)格與并行技術(shù)的電力系統(tǒng)動態(tài)安全評估[D];上海交通大學;2011年

，

本文編號：2311991